Picture for Wenhan Zhang

Wenhan Zhang

Filtered Randomized Smoothing: A New Defense for Robust Modulation Classification

Add code
Oct 08, 2024
Viaarxiv icon

Design and Implementation of A Soccer Ball Detection System with Multiple Cameras

Add code
Jan 31, 2023
Viaarxiv icon

SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models

Add code
Jun 04, 2019
Figure 1 for SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models
Figure 2 for SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models
Figure 3 for SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models
Viaarxiv icon

System Demo for Transfer Learning across Vision and Text using Domain Specific CNN Accelerator for On-Device NLP Applications

Add code
Jun 04, 2019
Figure 1 for System Demo for Transfer Learning across Vision and Text using Domain Specific CNN Accelerator for On-Device NLP Applications
Figure 2 for System Demo for Transfer Learning across Vision and Text using Domain Specific CNN Accelerator for On-Device NLP Applications
Figure 3 for System Demo for Transfer Learning across Vision and Text using Domain Specific CNN Accelerator for On-Device NLP Applications
Figure 4 for System Demo for Transfer Learning across Vision and Text using Domain Specific CNN Accelerator for On-Device NLP Applications
Viaarxiv icon

SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding

Add code
Jun 04, 2019
Figure 1 for SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding
Figure 2 for SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding
Viaarxiv icon

2-bit Model Compression of Deep Convolutional Neural Network on ASIC Engine for Image Retrieval

Add code
May 08, 2019
Figure 1 for 2-bit Model Compression of Deep Convolutional Neural Network on ASIC Engine for Image Retrieval
Figure 2 for 2-bit Model Compression of Deep Convolutional Neural Network on ASIC Engine for Image Retrieval
Figure 3 for 2-bit Model Compression of Deep Convolutional Neural Network on ASIC Engine for Image Retrieval
Figure 4 for 2-bit Model Compression of Deep Convolutional Neural Network on ASIC Engine for Image Retrieval
Viaarxiv icon

SuperTML: Two-Dimensional Word Embedding and Transfer Learning Using ImageNet Pretrained CNN Models for the Classifications on Tabular Data

Add code
Mar 22, 2019
Figure 1 for SuperTML: Two-Dimensional Word Embedding and Transfer Learning Using ImageNet Pretrained CNN Models for the Classifications on Tabular Data
Figure 2 for SuperTML: Two-Dimensional Word Embedding and Transfer Learning Using ImageNet Pretrained CNN Models for the Classifications on Tabular Data
Figure 3 for SuperTML: Two-Dimensional Word Embedding and Transfer Learning Using ImageNet Pretrained CNN Models for the Classifications on Tabular Data
Figure 4 for SuperTML: Two-Dimensional Word Embedding and Transfer Learning Using ImageNet Pretrained CNN Models for the Classifications on Tabular Data
Viaarxiv icon

Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis

Add code
Jan 24, 2019
Figure 1 for Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis
Figure 2 for Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis
Figure 3 for Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis
Figure 4 for Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis
Viaarxiv icon

Super Characters: A Conversion from Sentiment Classification to Image Classification

Add code
Oct 15, 2018
Figure 1 for Super Characters: A Conversion from Sentiment Classification to Image Classification
Figure 2 for Super Characters: A Conversion from Sentiment Classification to Image Classification
Figure 3 for Super Characters: A Conversion from Sentiment Classification to Image Classification
Figure 4 for Super Characters: A Conversion from Sentiment Classification to Image Classification
Viaarxiv icon

Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications

Add code
Apr 30, 2018
Figure 1 for Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications
Figure 2 for Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications
Figure 3 for Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications
Figure 4 for Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications
Viaarxiv icon